This is a very incomplete and subjective selection of resources to learn about the algorithms and maths of Artificial Intelligence (AI) / Machine Learning (ML) / Statistical Inference (SI) / Deep Learning (DL) / Reinforcement Learning (RL). It is aimed at beginners (those without Computer Science background and not knowing anything about these subjects) and hopes to take them to quite advanced levels (able to read and understand DL papers). It is not an exhaustive list and only contains some of the learning materials that I have personally completed so that I can include brief personal comments on them. It is also by no means the best path to follow (nowadays most MOOCs have full paths all the way from basic statistics and linear algebra to ML/DL). But this is the path I took and in a sense it's a partial documentation of my personal journey into DL (actually I bounced around all of these back and forth like crazy).

The field of study that focuses on the interactions between human language and computers is called Natural Language Processing, or NLP for short. It sits at the intersection of computer science, artificial intelligence, and computational linguistics (Wikipedia). "Nat ur al Lan guage Pro cessing is a field that cov ers com puter un der stand ing and ma nip u la tion of hu man lan guage, and it's ripe with pos sib il it ies for news gath er ing," Anthony Pesce said in Natural Language Processing in the kitchen. "You usu ally hear about it in the con text of ana lyz ing large pools of legis la tion or other doc u ment sets, at tempt ing to dis cov er pat terns or root out cor rup tion." NLP is a way for computers to analyze, understand, and derive meaning from human language in a smart and useful way.

Education technology has the power to revolutionize education but with the integration of artificial intelligence, experts believed that it can be more beneficial, particularly in higher education and online learning. In an era where modern technology has become a valuable influence in the lives of humans, it's safe to assume that technology will be able to enhance the learning experience of educators and students, especially in higher education and online learning. As experts combined education technology (EdTech) and artificial intelligence (AI), a powerful tool to potentially transform education has been born. Due to the pervasiveness of technology today, the way students communicate and entertain themselves have changed. But some experts believed that the implementation of education technology alone in schools, colleges and universities across the nation is not enough to revolutionize education.

Learn how to design a spam classifier using machine learning APIs with this webinar. Syed is an IT Engineering Manager with 14 years of experience in software development, technology management, IT strategy, technology consulting, and product development.

The combination of big data and machine learning is a revolutionary technology that can make a great impact on any industry if used in a proper way. In the field of healthcare it has great usage in cases like early disease detection, finding signs of early breakouts of epidemics, using clustering to figure out regions of epidemics (e.g. In this article, I have tried to explore the prediction of the existence of heart disease by using standard machine learning algorithms, and the big data toolset like Apache Spark, parquet, Spark mllib, and Spark SQL. The source code of this article is available on GitHub here. Also, you can check out the entire eclipse project from here.

Designed to help understand the fundamentals of DS & Algorithms really well. A must have for programming interviews.

In just three years, Variational Autoencoders (VAEs) have emerged as one of the most popular approaches to unsupervised learning of complicated distributions. VAEs are appealing because they are built on top of standard function approximators (neural networks), and can be trained with stochastic gradient descent. VAEs have already shown promise in generating many kinds of complicated data, including handwritten digits, faces, house numbers, CIFAR images, physical models of scenes, segmentation, and predicting the future from static images. This tutorial introduces the intuitions behind VAEs, explains the mathematics behind them, and describes some empirical behavior. No prior knowledge of variational Bayesian methods is assumed.

The ultimate goals of serious education games (SEG) are to facilitate learning and maximizing enjoyment during playing SEGs. In SEG development, there are normally two spaces to be taken into account: knowledge space regarding learning materials and content space regarding games to be used to convey learning materials. How to deploy the learning materials seamlessly and effectively into game content becomes one of the most challenging problems in SEG development. Unlike previous work where experts in education have to be used heavily, we proposed a novel approach that works toward minimizing the efforts of education experts in mapping learning materials to content space. For a proof-of-concept, we apply the proposed approach in developing an SEG game, named \emph{Chem Dungeon}, as a case study in order to demonstrate the effectiveness of our proposed approach. This SEG game has been tested with a number of users, and the user survey suggests our method works reasonably well.

In the last several decades, thousands of machine learning algorithms have been developed. Very often, the selection of an algorithm to solve a particular problem is driven more by the data scientist's familiarity with a small subset of available algorithms, than optimizing for predictive power or operational constraints. This is unsurprising: Newcomers to machine learning and veteran data scientists alike, may be overwhelmed by the multitude of machine learning algorithms and where and how it is most appropriate to use them. In this webinar, Daniel Emaasit will introduce Model-Based Machine Learning (MBML), an approach to machine learning which addresses these challenges. Daniel will discuss the various uses of MBML, from tasks such as classification, to regression and clustering, and how it allows data scientists to address the uncretainty inherent to real-world machine learning applications.

The Microsoft Bot Framework provides just what you need to build and connect intelligent bots that interact naturally wherever your users are talking, from text/sms to Skype, Slack, Office 365 mail and other popular services. This is a step-by-step guide which my colleague Peter Daukintis has developed this tutorial which walks you through the development of a Microsoft Bot in C# using the Bot Framework Connector SDK .NET template. You will need to have a Microsoft Band and have collected some sleep data using a Microsoft Band and have had that synchronised up to the Microsoft cloud as this tutorial uses the Bot Framework to provide access to that data. Heart Rate monitoring depends on the current Band mode, It only monitors hr continuously when in exercise mode (along with all other sensors), all of the other scenarios have pre-defined cadences that allow the data to have analytical relevance whilst only using the sensors as much as needed. This is the information that is sent to MS Health, and as such is available through the Cloud API, along with the curated information that is derived by MS Health, e.g sleep efficiency, recovery time, etc.